Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    text related to forums and online discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.39
    ⓧ
    -1.15
    /***
    -1.11
    <?
    -1.08
    
    -1.02
     springfox
    -0.98
    <?
    -0.94
    /*!
    -0.89
    /**
    -0.86
    #![
    -0.79
    POSITIVE LOGITS
     véhic
    0.77
     soulign
    0.71
     TokenType
    0.69
    '
    0.68
    uxx
    0.65
     Pamph
    0.65
    dison
    0.64
    arture
    0.64
     unspeak
    0.64
    gnition
    0.63
    Act Density 1.294%

    No Known Activations